© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45472
    Prev
    Next
    INDEX
    Explanations

    dreaming or fantasy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugly
    -0.80
    Outdoor
    -0.79
     "$@"
    -0.79
    །
    -0.79
    бири
    -0.77
    QED
    -0.77
    useEffect
    -0.75
    ニング
    -0.75
    磁盘
    -0.74
    Cols
    -0.74
    POSITIVE LOGITS
     dream
    3.39
     dreams
    3.23
     dreaming
    3.19
     dreamer
    2.78
    dream
    2.78
     fantasy
    2.44
     dreamy
    2.44
    dreaming
    2.42
     unrealistic
    2.42
     DREAM
    2.42
    Activations Density 0.041%

    No Known Activations